KR102300349B1 - Unmanned drone for automatically setting moving path according to detection situation, and operating method thereof - Google Patents

Abstract

An unmanned aerial vehicle is disclosed. The unmanned aerial vehicle includes a camera, a drive control unit to control the flight of the unmanned aerial vehicle, a communication unit for performing communication with at least one control server, and a processor. The processor controls the flight of the unmanned aerial vehicle according to a preset first route through the drive control unit, detects at least one object based on an image acquired through the camera during flight of the unmanned aerial vehicle, controls the flight of the unmanned aerial vehicle through the drive control unit in accordance with a second route for tracking the detected object when the object is detected, and transmits the location information of the unmanned aerial vehicle and the information on the second route to the control server through the communication unit. The present disclosure provides an unmanned aerial vehicle that performs communication with one or more control servers by changing a route according to a detection situation and shares a detection situation. The unmanned aerial vehicle and the operating method according to the present disclosure have the advantage of performing flexible situation sharing by automatically changing the movement route according to the object detection situation.

Description

An unmanned aerial vehicle that automatically sets a movement path according to the detection situation, and an operation method { UNMANNED DRONE FOR AUTOMATICALLY SETTING MOVING PATH ACCORDING TO DETECTION SITUATION, AND OPERATING METHOD THEREOF }

The present disclosure relates to an unmanned aerial vehicle for detection, and more particularly, to an unmanned aerial vehicle that changes a flight path based on an object detection situation.

Although a system for searching for missing persons by operating an unmanned aerial vehicle after an accident has been used in the past, the development of a system that performs detection and initial response by region using an unmanned aerial vehicle operating by major base or region is not abundant. it is not the case.

In particular, long-distance communication and control technology of an unmanned aerial vehicle that shares a situation with one or more control servers according to object detection needs to be built more specifically.

Registered Patent Publication No. 10-21868230000 (Drone Control System)

The present disclosure provides an unmanned aerial vehicle that performs communication with one or more control servers by changing a path according to a detection situation and shares a detection situation.

Objects of the present disclosure are not limited to the above-mentioned purposes, and other objects and advantages of the present disclosure that are not mentioned may be understood by the following description, and will be more clearly understood by examples of the present disclosure. Moreover, it will be readily apparent that the objects and advantages of the present disclosure may be realized by the means and combinations thereof indicated in the claims.

The unmanned aerial vehicle according to an embodiment of the present disclosure includes a camera, a driving control unit for controlling the flight of the unmanned aerial vehicle, a communication unit for performing communication with at least one control server, the camera, the driving control unit, and the communication unit connected to includes a processor. The processor controls, through the driving control unit, the flight of the unmanned aerial vehicle according to a preset first route, and detects at least one object based on the image obtained through the camera during the flight of the unmanned aerial vehicle. , when the object is detected, control the flight of the unmanned aerial vehicle through the driving control unit according to a second path for tracking the detected object, and obtain location information of the unmanned aerial vehicle and information on the second path It is transmitted to the control server through the communication unit.

When the object is detected, the processor communicates with at least one rescue moving body through the communication unit to identify a location of the rescue moving body, and when the rescue moving body is located within a preset distance from the sensed object, According to a third path for turning around the sensed object, the flight of the unmanned aerial vehicle may be controlled through the driving controller.

In addition, the processor identifies a control server closest to the location of the unmanned aerial vehicle among a plurality of control servers provided for each region, and displays the location information, information on the second path, and the image of the detected object. It can be transmitted to the identified control server through the communication unit.

Here, when the unmanned aerial vehicle is out of an area capable of communicating with the identified control server, the processor identifies the location of the detected object in real time, acquires images of the detected object in real time, and the unmanned aerial vehicle controls the driving control unit to move to an area communicable with the identified control server, and when the unmanned aerial vehicle reaches an area communicable with the identified control server, information on the identified location in real time and the real time may transmit the acquired images to the control server.

At this time, after the information on the location identified in real time and the images acquired in real time are transmitted to the control server, the processor moves to the predicted location of the object predicted based on the location identified in real time. The driving control unit may be controlled to move the aircraft.

In this case, the processor may determine the expected position of the object by inputting the identified position in real time to at least one artificial intelligence model trained to predict a movement path.

Meanwhile, the processor controls the driving controller to move the unmanned aerial vehicle to at least one charging point when the remaining battery level of the unmanned aerial vehicle is less than a first threshold while the unmanned aerial vehicle is flying in the first route, , when the remaining battery level of the unmanned aerial vehicle is less than a second threshold that is smaller than the first threshold while the unmanned aerial vehicle is flying in the second path as the object is detected, the unmanned aerial vehicle moves to at least one charging point The driving control unit may be controlled to do so.

A method of operating an unmanned aerial vehicle according to an embodiment of the present disclosure includes the steps of moving along a preset first path, detecting at least one object based on an image acquired through a camera while the unmanned aerial vehicle is moving , when the object is detected, moving along a second path for tracking the detected object, transmitting the location information of the unmanned aerial vehicle and information on the second path to at least one control server do.

The unmanned aerial vehicle and the operating method according to the present disclosure have the advantage of performing fluid situation sharing by automatically changing the movement path according to the object detection situation.

The unmanned aerial vehicle and the operation method according to the present disclosure have the effect of increasing the accuracy and efficiency of detection through an algorithm that comprehensively reflects a communication state, a field of view condition, a battery, and the like.

1 is a view for explaining an operation of an unmanned aerial vehicle performing communication with at least one control server and detecting a path according to an embodiment of the present disclosure;
2 is a block diagram for explaining the configuration of an unmanned aerial vehicle according to an embodiment of the present disclosure;
3 is a flowchart for explaining an operation (operation method) of an unmanned aerial vehicle according to an embodiment of the present disclosure;
4 is a view for explaining an operation of performing a turning flight based on a detected object by an unmanned aerial vehicle according to an embodiment of the present disclosure;
5 is a diagram for explaining an operation of sequentially performing information collection and situation sharing by an unmanned aerial vehicle according to a communication distance with a control server according to an embodiment of the present disclosure; and
6 is a block diagram illustrating the configuration of an unmanned aerial vehicle according to various embodiments of the present disclosure.

Before describing the present disclosure in detail, a description will be given of the description of the present specification and drawings.

First, terms used in the present specification and claims have been selected in consideration of functions in various embodiments of the present disclosure. However, these terms may vary depending on the intention of a person skilled in the art, legal or technical interpretation, and emergence of new technology. Also, some terms are arbitrarily selected by the applicant. These terms may be interpreted in the meaning defined in the present specification, and if there is no specific term definition, it may be interpreted based on the general content of the present specification and common technical common sense in the art.

Also, the same reference numerals or reference numerals in each drawing attached to this specification indicate parts or components that perform substantially the same functions. For convenience of description and understanding, the same reference numerals or reference numerals are used in different embodiments. That is, even though all components having the same reference number are illustrated in a plurality of drawings, the plurality of drawings do not mean one embodiment.

In addition, in this specification and claims, terms including an ordinal number such as “first” and “second” may be used to distinguish between elements. This ordinal number is used to distinguish the same or similar elements from each other, and the meaning of the term should not be construed as limited due to the use of the ordinal number. As an example, the use order or arrangement order of the components combined with the ordinal number should not be limited by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, the singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as "comprises" or "consisting of" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and are intended to indicate that one or more other It is to be understood that this does not preclude the possibility of addition or presence of features or numbers, steps, operations, components, parts, or combinations thereof.

In an embodiment of the present disclosure, terms such as “module”, “unit”, “part”, etc. are terms used to refer to a component that performs at least one function or operation, and these components are hardware or software. It may be implemented or implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, and are integrated into at least one processor, except when each needs to be implemented in individual specific hardware. can be implemented as

In addition, in an embodiment of the present disclosure, when it is said that a certain part is connected to another part, this includes not only direct connection but also indirect connection through another medium. In addition, the meaning that a certain part includes a certain component means that other components may be further included, rather than excluding other components, unless otherwise stated.

1 is a diagram for explaining an operation of detecting a path while communicating with at least one control server by an unmanned aerial vehicle according to an embodiment of the present disclosure.

Referring to FIG. 1 , the unmanned aerial vehicle 100 may perform communication with at least one of a plurality of control servers 200 - 1 , 2 , ... provided for each region.

Specifically, the unmanned aerial vehicle 100 may identify the location of the unmanned aerial vehicle 100 using various sensors such as a global positioning system (GPS), and transmit the location information of the unmanned aerial vehicle 100 to the control server 200 . can

In addition, the unmanned aerial vehicle 100 may set a flight path or flight time based on a control signal received from the control server 200 .

The unmanned aerial vehicle 100 may fly and detect various routes such as at least one coastal zone, a danger zone, and other various reconnaissance or detection zones.

Meanwhile, referring to FIG. 1 , the unmanned aerial vehicle 100 is a control server 200-1 closest to the current location of the unmanned aerial vehicle 100 among a plurality of control servers 200-1, 2, ... provided for each region. can communicate with

Alternatively, the unmanned aerial vehicle 100 may communicate with the control server 200 - 1 closest to the route 11 on which the unmanned aerial vehicle 100 is currently flying.

Alternatively, the unmanned aerial vehicle 100 is set to manage a region including the current location or current flight path of the unmanned aerial vehicle 100 among a plurality of control servers 200-1, 2, ... for managing different regions. Communication with the control server 200 - 1 may be performed.

The unmanned aerial vehicle 100 may transmit information about an image of an object detected during detection, the position of the object, and the location/path of the unmanned aerial vehicle 100 to the control server 200 - 1 .

Referring to FIG. 1 , when a specific object 12 such as a missing person or a person in distress is detected during the detection of the path 11 , the unmanned aerial vehicle 100 performs a flight according to the path for tracking the object 12 and detects the object. can be monitored.

Also, the unmanned aerial vehicle 100 may transmit an image of an object and location information of the object to the control server 200 - 1 .

As such, the unmanned aerial vehicle 100 according to the present disclosure automatically changes the path according to the detection situation of the object and shares the situation, so that it is possible to actively detect and transmit meaningful data to the control server.

Hereinafter, the configuration and operation of the unmanned aerial vehicle 100 according to the present disclosure will be described in more detail with reference to the drawings.

2 is a block diagram illustrating the configuration of an unmanned aerial vehicle according to an embodiment of the present disclosure.

Referring to FIG. 2 , the unmanned aerial vehicle 100 may include a camera 110 , a communication unit 120 , a driving control unit 130 , a processor 140 , and the like.

The camera 110 is configured to acquire various images of the external environment.

The camera 110 may include various types of cameras, such as an RGB camera, a Time of Flight (TOF) camera, a thermal camera, and a stereo camera.

The camera 110 may include a camera having various viewing angles, and may include a plurality of cameras.

Meanwhile, although not shown, the unmanned aerial vehicle 100 may include at least one light output unit for assisting in capturing the camera 110 . The light output unit may include at least one light emitting diode (LED) or other laser output means, but is not limited thereto.

In this case, the processor 140 may control the light output unit to output light to the point where the camera 110 shoots when the camera 110 is photographed, and as a result, detection using the photographing of the camera 110 is possible even at night. It has the effect that it is possible.

The communication unit 120 is a configuration for the unmanned aerial vehicle 100 to transmit and receive data to and from various external devices, and may include at least one circuit for communication.

Specifically, the communication unit 120 may communicate with the control servers 200-1, 2, ..., a rescue team server, a rescue boat, an air vehicle, a rescue vehicle, another unmanned aerial vehicle, and various other terminals.

The communication unit 120 is TCP/IP (Transmission Control Protocol/Internet Protocol), UDP (User Datagram Protocol), HTTP (Hyper Text Transfer Protocol), HTTPS (Secure Hyper Text Transfer Protocol), FTP (File Transfer Protocol), SFTP ( A communication protocol (protocol) such as Secure File Transfer Protocol) and MQTT (Message Queuing Telemetry Transport) may be used to transmit/receive various information to and from one or more external electronic devices.

To this end, the communication unit 120 may be connected to an external device based on a network implemented through wireless communication. In this case, the communication unit 120 may be directly connected to an external device, or may be connected to an external electronic device through one or more external servers (eg, Internet Service Providers (ISPs)) that provide a network.

The network may be a personal area network (PAN), a local area network (LAN), a wide area network (WAN), etc. depending on the area or size, and depending on the openness of the network, an intranet, It may be an extranet or the Internet.

Wireless communication includes long-term evolution (LTE), LTE Advance (LTE-A), 5th generation (5G) mobile communication, code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), at least one of the communication methods such as Zigbee may include

Here, the communication unit 120 may include a network interface or a network chip according to the aforementioned wireless communication method. Meanwhile, the communication method is not limited to the above-described example, and may include a communication method newly appearing according to the development of technology.

The driving control unit 130 is configured to control the flight of the unmanned aerial vehicle 100 . The drive control unit 130 includes take-off and landing of the unmanned aerial vehicle 100, movement of the unmanned aerial vehicle 100 in a three-dimensional direction, and rotation of the unmanned aerial vehicle 100 in a pitch, roll, yaw direction, etc. can be controlled.

For example, the driving control unit 130 may include at least one control circuit for controlling a rotation motor for driving the rotation of each propeller provided in the unmanned aerial vehicle 100 . Also, the driving control unit 130 may drive at least one engine (eg, a jet engine) provided in the unmanned aerial vehicle 100 .

Processor 140 is a configuration for controlling the overall configuration included in the unmanned aerial vehicle 100, CPU (Central Processing Unit), AP (Application Processor), GPU (Graphic Processing Unit), VPU (Video Processing Unit), NPU (Neural Processing Unit) may be composed of various units.

For example, the processor 140 may control each configuration of the unmanned aerial vehicle 100 by executing instructions stored in the memory of the unmanned aerial vehicle 100 .

Hereinafter, an operation of the unmanned aerial vehicle 100 under the control of the processor 140 according to various embodiments of the present disclosure will be described with reference to the drawings.

3 is a flowchart illustrating an operation of an unmanned aerial vehicle according to an embodiment of the present disclosure.

Referring to FIG. 3 , the unmanned aerial vehicle 100 may move along a preset first route ( S310 ).

Here, the preset first route may correspond to a route for reconnaissance or detection of various zones, such as a coastal zone, a sea zone, a mountain zone, and a danger zone.

The preset first path may be set through at least one control server.

As an example, the control server may select at least one area in which accidents occur frequently according to accident occurrence histories for a plurality of areas included on the map, and set the corresponding area as a route for the flight of the unmanned aerial vehicle 100 .

As another example, the control server may receive a user input for setting at least one flight path on the map, and may transmit the flight path set according to the user input to the unmanned aerial vehicle 100 . Here, the user input may be received through a user input unit provided in the control server or may be received through at least one terminal device capable of communicating with the control server 100 .

As another example, the control server may set the flight route based on the accident point. In this case, the control server may set a new route for patrolling an area within a certain distance from the accident point.

Alternatively, the unmanned aerial vehicle 100 may directly set a route based on the information on the accident point received from the control server.

The processor 140 may identify the location information of the unmanned aerial vehicle 100 through a GPS sensor or the like, and may transmit the real-time movement route and real-time location information to the control server through the communication unit 120 . In this case, the processor 140 may communicate with a control server closest to the unmanned aerial vehicle 100 among a plurality of control servers provided for each region.

In addition, the unmanned aerial vehicle 100 may detect at least one object based on an image acquired through the camera 110 during flight of the first route ( S320 ).

As an example, the processor 140 may identify whether an object of a preset shape or a preset color exists in the image acquired through the camera 110 .

As an example, the processor 140 may analyze the image to identify whether an object having a preset shape (eg, a human shape, an animal shape, a ship shape, an aircraft shape, etc.) exists in the image.

Here, the processor 140 may use at least one module or an artificial intelligence model for identifying an object having a preset shape. Specifically, the processor 140 may input an image captured by the camera 110 into the above-described artificial intelligence model, and detect whether an object having a preset shape exists.

The artificial intelligence model may be a model trained to identify a shape based on an image including various objects (eg, people, animals, ships, flying vehicles, etc.) having a preset shape. Here, each image may be used for training while the contour or shape of the object included in each image is marked, but is not limited thereto.

Also, the processor 140 may acquire a depth image through the depth camera, and identify the shape of each object included in the acquired depth image. In this case, the processor 140 may determine whether an object having a preset shape exists.

In addition, the processor 140 may detect whether an object of a preset color exists based on the R/G/B value for each pixel of the image captured by the RGB camera.

For example, information on a preset color (eg, red, white, etc.) that is difficult to exist in a natural terrain without human traces may be pre-stored in the memory of the unmanned aerial vehicle 100 .

In this case, the processor 140 identifies whether the R/G/B value of at least one pixel in the image matches a preset color, and when there are more than a threshold number of pixels matching the preset color in the image, It may be determined that at least one object exists.

Also, according to an embodiment, the processor 140 may input an image to an artificial intelligence model trained to identify at least one preset object, and recognize at least one object based on the output of the artificial intelligence model.

This artificial intelligence model may be a model trained to identify an object based on a plurality of images including a preset object (eg, a person, an animal, a ship, a flying vehicle, etc.), for example, this artificial intelligence model is a CNN It is composed of (Convolutional Neural Network) and can operate as a classifier that outputs the type of object included in the image.

Also, according to an embodiment, the processor 140 may detect at least one object based on a thermal image captured by the thermal camera. The thermal camera may be, for example, an infrared-based camera, but is not limited thereto. Through the thermal camera, the unmanned aerial vehicle 100 may detect various objects even at night.

As a specific example, the processor 140 may detect at least one object having a preset temperature range matching the body temperature of a human or an animal in the thermal image.

In this case, the processor 140 may acquire the RGB image by photographing the region including the object detected through the thermal image with the RGB camera. In addition, the processor 140 may recognize the object by analyzing the image captured by the RGB camera.

As such, when an object is detected according to the above-described various embodiments, the unmanned aerial vehicle 100 may move along a second path for tracking the detected object (S330).

Here, the second path may correspond to a path for tracking the object according to the movement of the sensed object or a path for turning around the sensed object.

For example, the processor 140 acquires a plurality of images by controlling the camera 110 to capture an image of the object in real time, and determines the movement direction of the object based on a change in the position of the object included in the plurality of images. can be identified.

In this case, the processor 140 may control the driving controller 130 to move the unmanned aerial vehicle 100 according to the movement direction of the identified object.

As another example, the processor 140 may control the driving controller 130 by setting a path for turning an area within a predetermined distance based on the position of the detected object.

Meanwhile, the unmanned aerial vehicle 100 may fly along a third path for turning around the object when at least one rescue moving object approaches while flying along the second path for tracking the detected object. In this regard, a specific embodiment will be described later with reference to FIG. 4 .

In addition, the processor 140 may transmit the location information of the unmanned aerial vehicle 100 and information on the second route to the control server (S340). In this case, the processor 140 may transmit information on the sensed or recognized object together.

As a result, the control server may identify the location (discovery location) of the object according to the location information of the unmanned aerial vehicle 100 , and may identify the changed second path of the unmanned aerial vehicle 100 . In addition, the control server may identify the moving state and/or the moving direction of the object based on the second path of the unmanned aerial vehicle 100 tracking the object.

Meanwhile, FIG. 4 is a diagram for explaining an operation in which an unmanned aerial vehicle performs a turning flight based on a detected object according to an embodiment of the present disclosure.

Referring to FIG. 4 , the processor 140 may communicate with the rescue movable body 400 through the communication unit 120 to identify the location of the rescue movable body 400 .

In this case, the processor 140 may transmit a rescue request to the rescue mobile 400 through the communication unit 120 , and may also transmit location information of the object. In this case, the processor 140 may directly communicate with the rescue mobile 400 through the communication unit 120 or transmit a rescue request through the control server.

The rescue moving body 400 may correspond to a rescue vessel, a rescue vehicle, a rescue vehicle, and the like, and may include at least one module for communicating with the unmanned aerial vehicle 100 .

In addition, when the structural movable body 400 is located within a predetermined distance from the detected object 11 , the processor 140 performs the driving control unit 130 according to the third path 410 for turning around the detected object. ) through which the flight of the unmanned aerial vehicle 100 can be controlled.

That is, the unmanned aerial vehicle 100, which was flying on the second path that tracks the object as the object is detected, can fly on the third path 410 that turns around the object as the rescue moving body 400 approaches, As a result, there is an advantage that the sensor of the rescue moving body 400 or the rescue team personnel riding the rescue moving body 400 can quickly discover the location of the object based on the orbiting flight of the unmanned aerial vehicle 100 .

Here, the unmanned aerial vehicle 100 may turn in a circle around a point as high as the altitude of the unmanned aerial vehicle 100 in the vertical direction from the point where the sensed object is located. Alternatively, the unmanned aerial vehicle 100 draws a circle centered on a point higher by the altitude of the unmanned aerial vehicle 100 in the vertical direction from a point moved by a certain distance in the direction of the structural movable body 400 from the point where the detected object is located. You can draw and turn.

Here, the radius of the circle drawn by the unmanned aerial vehicle 100 while turning may be set differently depending on the viewing state.

For example, the visibility state may be divided into a plurality of stages according to the degree of fog or the concentration of fine dust. Here, it may be defined that the higher the level of the visual field, the easier it is to secure the peripheral field of view. That is, as the fog is less and clearer and the concentration of fine dust is lower, the level of the visibility state may be higher.

In this case, the processor 140 may identify the viewing state based on the surrounding image captured by the camera 110 .

Here, the processor 140 may analyze each pixel value included in the image to identify noise (eg, fog, fine dust) included in the image, and may determine the level of the viewing state to be lower as the amount of noise increases.

Alternatively, the processor 140 may use at least one artificial intelligence model trained to determine the visual field state. This AI model uses images corresponding to each stage of the visual field (ex. images on a clear day, an image on a cloudy day, an image on a foggy day, an image on a day with high fine dust concentration, etc.) It may be a model trained to determine the visual field state based on the

In addition, the processor 140 may set the path of the turning flight of the unmanned aerial vehicle 100 based on the determined stage of the visual field state. Specifically, as the level of the visibility state is lower (the visibility state is poor), the processor 140 may control the unmanned aerial vehicle 100 to turn in a circle having a larger radius.

In this case, the possibility that the rescue vehicle 400 will discover the unmanned aerial vehicle 100 is increased in weather conditions with poor visibility. On the other hand, in the case of a clear day in which the unmanned aerial vehicle 100 can be easily found, as the radius of the path in which the unmanned aerial vehicle 100 revolves around the object becomes narrower, the rescue vehicle 400 that discovers the unmanned aerial vehicle 100 has the advantage of being able to quickly identify the location of an object.

Thereafter, when information indicating that an object has been found from the rescue moving body 400 is received, the processor 140 flies the unmanned aerial vehicle 100 according to at least one detection path (eg, a first path) for detecting another object. can be controlled.

Meanwhile, FIG. 5 is a diagram for explaining an operation of sequentially performing information collection and situation sharing by an unmanned aerial vehicle according to whether communication with a control server is possible according to an embodiment of the present disclosure.

5, the unmanned aerial vehicle 100 communicates with the control server 200-1 closest to the location of the unmanned aerial vehicle 100 among a plurality of control servers 200-1, 2, ... provided for each region. can be done

However, at least a portion of the detection path of the unmanned aerial vehicle 100 may deviate from an area in which communication is possible between the unmanned aerial vehicle 100 and the control server 200 - 1 .

Whether the communication is out of the area may be determined in real time through the unmanned aerial vehicle 100 .

Specifically, the unmanned aerial vehicle 100 transmits information on the location and route of the unmanned aerial vehicle 100 in real time to the control server 200-1, while at least one response signal or A control signal may be received.

Here, when the transmission speed of data/signal transmitted and received with the control server 200-1 is less than the threshold speed, or the successful transmission/reception ratio of data/signal is less than the threshold, or the reception sensitivity of the data/signal is less than the threshold sensitivity, The processor 140 may identify that the unmanned aerial vehicle 100 is out of an area capable of communicating with the control server 200 - 1 .

As such, the unmanned aerial vehicle 100, which has been detecting a path outside the communication range with the control server 200-1, may detect at least one object as shown in FIG. 5 (S510). Alternatively, the unmanned aerial vehicle 100 may detect an object within the communicable area and then leave the communicable area while tracking the object.

In this case, the unmanned aerial vehicle 100 may identify the location of the object in real time through at least one sensor (eg, a GPS sensor), and the image of the detected object may also be captured and stored in real time through the camera 110 . There is (S520).

Then, the unmanned aerial vehicle 100 may move back to a communicable area (S530).

Specifically, when the storage amount of the object image is greater than or equal to a certain capacity, or the number of stored object images is greater than or equal to a certain number, the processor 140 stops the tracking of the object and moves the unmanned aerial vehicle 100 to a communicable area. The driving control unit 130 may be controlled.

Here, the unmanned aerial vehicle 100 may determine whether communication with the control server is possible in real time while moving in the direction in which the control server is located.

Thereafter, the unmanned aerial vehicle 100 that has reached the communicable area may transmit information about the location identified in real time and images acquired (stored) in real time to the control server 200 - 1 ( S540 ).

Then, the unmanned aerial vehicle 100 may move back to the expected position of the object ( S550 ).

The predicted location may be predicted based on the location of the previously identified object in real time.

As an example, the processor 140 of the unmanned aerial vehicle 100 determines the expected position of the object by inputting the identified (by time) position in real time prior to at least one artificial intelligence model trained to predict the movement path. can

In addition, the processor 140 may input information about the location of the object by time and the terrain in which the object is located into the AI model. The information on the topography may include information on whether each point is on the water or on the ground, and information on the water depth or altitude of each point.

In this case, the artificial intelligence model may predict the location of the object in the future based on the location of the object by time in the terrain.

This artificial intelligence model may be a model trained based on information on the temporal position of at least one moving object (eg, a record of the temporal position of an actual survivor in the past), and may be a Recurrent Neural Network (RNN) model. However, the present invention is not limited thereto.

In addition, this artificial intelligence model may be a model trained based on information on the terrain where the object was located (ex. information on the terrain where the actual distressed in the past) in addition to information on the location of the object by time. .

As another example, the predicted location of the object may be determined through the control server 200 that has received information on the real-time location of the object from the unmanned aerial vehicle 100 . In this case, the control server 200 may transmit a control signal to cause the unmanned aerial vehicle 100 to move to the expected location.

The unmanned aerial vehicle 100 that has moved to the expected location according to at least one of the above-described embodiments may resume detection of the object as the object is rediscovered.

In this case, the unmanned aerial vehicle 100 may delete information and images on the real-time location of the object that have already been transmitted to the control server 200 - 1 in the memory. As a result, as the tracking of the object is resumed, information on the real-time location of the object and the image of the object newly collected may be stored in the memory without a capacity problem.

Meanwhile, the unmanned aerial vehicle 100 may move to at least one charging point according to the remaining battery level. In relation to this, information on the location of at least one charging point may be stored in the memory of the unmanned aerial vehicle 100, and the unmanned aerial vehicle 100 may move to the nearest charging point to the unmanned aerial vehicle 100 according to the remaining battery level. have.

Specifically, when the remaining battery level of the unmanned aerial vehicle 100 in flight is less than a threshold, the processor 140 may control the driving controller 130 to move the unmanned aerial vehicle 100 to the nearest charging point.

In this case, the processor 140 may calculate the threshold in real time according to the distance between the nearest charging point and the unmanned aerial vehicle 100 . As a specific example, the processor 140 identifies a value obtained by multiplying the battery usage per unit distance movement of the unmanned aerial vehicle 100 by the distance to the charging point, and sets the threshold of the battery to match the amount of energy obtained by multiplying the identified value by 120%. may be set, but is not limited thereto.

Also, the processor 140 may differently set a threshold ratio of the battery related to the time of moving to the charging point according to whether an object is detected.

For example, when the remaining battery level of the unmanned aerial vehicle 100 is less than the first threshold while the unmanned aerial vehicle 100 is flying on the first path that is the detection path, the processor 140 moves the unmanned aerial vehicle 100 to the charging point. The driving control unit 130 may be controlled to do so.

On the other hand, when the unmanned aerial vehicle 100 is flying in the second route (: object tracking) as an object is detected while flying in the first route, the remaining battery level of the unmanned aerial vehicle 100 is smaller than the first threshold second threshold. On the premise that it is less than, the processor 140 may control the driving control unit 130 to move the unmanned aerial vehicle 100 to the charging point.

That is, when the object is detected and the flight is tracking, the movement to the charging point may be relatively delayed compared to the case of the general detection flight in which the object is not detected. As a result, tracking of the detected object may proceed more smoothly.

However, even if the second threshold is smaller than the first threshold, since the unmanned aerial vehicle 100 should not be discharged without reaching the charging point, the second threshold is charged to the battery usage per unit distance of the unmanned aerial vehicle 100 . It should be set to be larger than the amount of energy multiplied by the distance to the point.

Meanwhile, FIG. 6 is a block diagram illustrating the configuration of an unmanned aerial vehicle according to various embodiments of the present disclosure.

The unmanned aerial vehicle 100 may further include a sensor unit 150 , a memory 160 , and the like in addition to the camera 110 , the communication unit 120 , the driving control unit 130 , and the processor 140 .

The sensor unit 150 may include various types of sensors for acquiring information about the surrounding environment. Specifically, the sensor unit 150 may include a GPS sensor, a geomagnetic sensor, an acceleration sensor, a wind direction/wind speed sensor, a lidar sensor, and the like.

The processor 140 may control the driving controller 130 to drive the flight of the unmanned aerial vehicle 100 based on the sensing data obtained through the above-described various sensors.

Specifically, the processor 140 may identify and adjust the position, speed, acceleration, direction, etc. of the unmanned aerial vehicle 100 in real time through the sensor unit 150 .

The processor 140 may acquire an image through the camera 110 as at least one object is detected based on the sensing data. For example, when at least one object is detected through sensing data obtained through the lidar sensor, the processor 140 may control the camera 110 to photograph the detected object. In this case, the processor 140 may recognize the object by analyzing the image acquired through the camera 110 .

The memory 160 is a configuration for storing an operating system (OS) for controlling the overall operation of the components in the unmanned aerial vehicle 100 , at least one instruction, and data.

The memory 160 may include non-volatile memory such as ROM and flash memory, and may include volatile memory such as DRAM. Also, the memory 160 may include a hard disk, a solid state drive (SSD), or the like.

The memory 160 may store the artificial intelligence model according to the various embodiments described above. The memory 160 is a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), GAN (Generative Adversarial Network) and Deep Q-Networks may include, but are not limited to, various artificial intelligence models.

The memory 160 may store an image of an object photographed through the camera 110, information on the real-time location of the object, information on the real-time location of the unmanned aerial vehicle 100, information on at least one preset route, and the like. have.

Meanwhile, the various embodiments described above may be implemented by combining a plurality of embodiments as long as they do not conflict with each other.

Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described in the present disclosure are ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays) ), processors, controllers, micro-controllers, microprocessors, and other electrical units for performing other functions may be implemented using at least one.

In some cases, the embodiments described herein may be implemented by the processor itself. According to the software implementation, embodiments such as the procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

Meanwhile, computer instructions or a computer program for performing a processing operation in each device according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. can When the computer instructions or computer program stored in such a non-transitory computer-readable medium are executed by the processor of a specific device such as an unmanned aerial vehicle, the specific device performs the operation of the unmanned aerial vehicle according to the various embodiments described above.

The non-transitory computer-readable medium refers to a medium that stores data semi-permanently, rather than a medium that stores data for a short moment, such as a register, cache, memory, etc., and can be read by a device. Specific examples of the non-transitory computer-readable medium may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

In the above, preferred embodiments of the present disclosure have been illustrated and described, but the present disclosure is not limited to the specific embodiments described above, and it is common in the technical field pertaining to the present disclosure without departing from the gist of the present disclosure as claimed in the claims. Various modifications may be made by those having the knowledge of

100: drone 110: camera
120: communication unit 130: drive control unit
140: processor

Claims (8)

In the unmanned aerial vehicle,
camera;
a driving control unit for controlling the flight of the unmanned aerial vehicle;
a communication unit for performing communication with at least one control server; and
Including a; processor connected to the camera, the driving control unit, and the communication unit;
The processor is
Controlling the flight of the unmanned aerial vehicle according to a preset first route through the driving control unit,
Detect at least one object based on the image acquired through the camera during the flight of the unmanned aerial vehicle,
When the object is detected, the flight of the unmanned aerial vehicle is controlled through the driving controller according to a second path for tracking the detected object,
Transmitting the location information of the unmanned aerial vehicle and information on the second route to the control server through the communication unit,
The processor is
Identifies the control server closest to the location of the unmanned aerial vehicle among a plurality of control servers provided for each region,
An unmanned aerial vehicle that transmits the location information, the information on the second path, and the image of the detected object to the identified control server through the communication unit. According to claim 1,
The processor is
When the object is detected, the communication unit communicates with at least one mobile rescue body to identify the location of the rescue mobile body,
When the rescue moving object is located within a preset distance from the sensed object, the unmanned aerial vehicle controls the flight of the unmanned aerial vehicle through the driving controller according to a third path for turning around the sensed object. delete According to claim 1,
The processor is
When the unmanned aerial vehicle is out of an area capable of communicating with the identified control server, the location of the detected object is identified in real time, and images of the detected object are acquired in real time,
controlling the driving control unit to move the unmanned aerial vehicle to an area capable of communicating with the identified control server,
When the unmanned aerial vehicle reaches an area capable of communicating with the identified control server, the information on the location identified in real time and the images acquired in real time are transmitted to the control server. 5. The method of claim 4,
The processor is
After the information on the location identified in real time and the images obtained in real time are transmitted to the control server, the driving to move the unmanned aerial vehicle to the predicted location of the object predicted based on the location identified in real time A drone that controls the control unit. 6. The method of claim 5,
The processor is
An unmanned aerial vehicle that determines an expected position of the object by inputting the identified position in real time to at least one artificial intelligence model trained to predict a movement path. According to claim 1,
The processor is
When the remaining battery level of the unmanned aerial vehicle is less than a first threshold in a state in which the unmanned aerial vehicle is flying in the first route, controlling the driving control unit to move the unmanned aerial vehicle to at least one charging point,
When the remaining battery level of the unmanned aerial vehicle is less than a second threshold that is smaller than the first threshold while the unmanned aerial vehicle is flying in the second path as the object is detected, the unmanned aerial vehicle moves to at least one charging point An unmanned aerial vehicle that controls the drive control unit. In the operation method of the unmanned aerial vehicle,
moving according to a first preset path;
detecting at least one object based on an image acquired through a camera while the unmanned aerial vehicle is moving;
when the object is detected, moving along a second path for tracking the detected object; and
Transmitting the location information of the unmanned aerial vehicle and information on the second route to at least one control server; includes,
The step of transmitting to the control server is,
Identifies the control server closest to the location of the unmanned aerial vehicle among a plurality of control servers provided for each region,
Transmitting the location information, the information on the second path, and the image of the detected object to the identified control server, the operation method of the unmanned aerial vehicle.

Images